lesso11 commited on
Commit
122d497
·
verified ·
1 Parent(s): 0ab5548

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1a17c4522cfe8c9a08f66ea0adae93b53ab4f4a004585f14b0c8ab71f33f9eb
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e755f38609a258ed8fede5a7666680bc480d363cd8556056f38a798326c3fb
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c738a1f73b1fa9d7b5f40ae21c6b3a63d1f761e7116fd20d5b46967b5ecffdf
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd41597d878255002082ddcc105161c7813334fb0f1e8a3449f732b54505519
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b89dd38db98ad38a01577cdd46c96a298f4583db1a347ee24c5352fb1155451
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde104bab0adc1cc90c60a95e124ce8958368abce247283c13e815fc5610de65
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.01686719892049927,
5
  "eval_steps": 9,
6
- "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -604,6 +604,205 @@
604
  "learning_rate": 1.7860619515673033e-05,
605
  "loss": 0.0021,
606
  "step": 75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
607
  }
608
  ],
609
  "logging_steps": 1,
@@ -618,12 +817,12 @@
618
  "should_evaluate": false,
619
  "should_log": false,
620
  "should_save": true,
621
- "should_training_stop": false
622
  },
623
  "attributes": {}
624
  }
625
  },
626
- "total_flos": 1.097993179669463e+17,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02248959856066569,
5
  "eval_steps": 9,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
604
  "learning_rate": 1.7860619515673033e-05,
605
  "loss": 0.0021,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.017092094906105925,
610
+ "grad_norm": 0.21683244407176971,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 0.0055,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.017316990891712583,
617
+ "grad_norm": 0.4317927956581116,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 0.0152,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.01754188687731924,
624
+ "grad_norm": 0.09037106484174728,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 0.0017,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.017766782862925896,
631
+ "grad_norm": 0.21414412558078766,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 0.0079,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.017991678848532554,
638
+ "grad_norm": 0.11598372459411621,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 0.0019,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.018216574834139212,
645
+ "grad_norm": 0.18292973935604095,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 0.0033,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.018216574834139212,
652
+ "eval_loss": 0.005181905347853899,
653
+ "eval_runtime": 818.2261,
654
+ "eval_samples_per_second": 4.577,
655
+ "eval_steps_per_second": 0.573,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.018441470819745866,
660
+ "grad_norm": 0.37185707688331604,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 0.0087,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.018666366805352524,
667
+ "grad_norm": 0.08201336115598679,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 0.0024,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.018891262790959183,
674
+ "grad_norm": 0.11379610002040863,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 0.0033,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.019116158776565837,
681
+ "grad_norm": 0.1044936403632164,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 0.0021,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.019341054762172495,
688
+ "grad_norm": 0.299877405166626,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 0.0048,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.019565950747779153,
695
+ "grad_norm": 0.039606399834156036,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 0.0011,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.019790846733385808,
702
+ "grad_norm": 0.1582029163837433,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 0.0047,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.020015742718992466,
709
+ "grad_norm": 0.2292255014181137,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 0.0033,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.020240638704599124,
716
+ "grad_norm": 0.07060254365205765,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 0.0019,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.020240638704599124,
723
+ "eval_loss": 0.004966777749359608,
724
+ "eval_runtime": 818.3255,
725
+ "eval_samples_per_second": 4.576,
726
+ "eval_steps_per_second": 0.573,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.02046553469020578,
731
+ "grad_norm": 0.0997166708111763,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 0.0035,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.020690430675812437,
738
+ "grad_norm": 0.0572785846889019,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 0.0027,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.020915326661419095,
745
+ "grad_norm": 0.18832778930664062,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 0.0106,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.02114022264702575,
752
+ "grad_norm": 0.14147458970546722,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 0.0078,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.021365118632632407,
759
+ "grad_norm": 0.08944231271743774,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 0.0047,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.021590014618239065,
766
+ "grad_norm": 0.07234779745340347,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 0.0009,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.02181491060384572,
773
+ "grad_norm": 0.3288421034812927,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 0.0055,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.022039806589452378,
780
+ "grad_norm": 0.09930330514907837,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 0.0017,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.022264702575059036,
787
+ "grad_norm": 0.45012977719306946,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 0.0016,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.022264702575059036,
794
+ "eval_loss": 0.004946997854858637,
795
+ "eval_runtime": 818.2178,
796
+ "eval_samples_per_second": 4.577,
797
+ "eval_steps_per_second": 0.573,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.02248959856066569,
802
+ "grad_norm": 0.10031512379646301,
803
+ "learning_rate": 0.0,
804
+ "loss": 0.0014,
805
+ "step": 100
806
  }
807
  ],
808
  "logging_steps": 1,
 
817
  "should_evaluate": false,
818
  "should_log": false,
819
  "should_save": true,
820
+ "should_training_stop": true
821
  },
822
  "attributes": {}
823
  }
824
  },
825
+ "total_flos": 1.4652273850318848e+17,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null